View article

Imagine that hundreds of video streams, taken by mobile phones during a rock concert, are uploaded to a server. One attractive application of such prominent dataset is to allow a user to create his own video with a deliberately chosen but virtual camera trajectory. This is the challenge addressed by the Scenenet project, programme FET‐Open SME (GA 309169). One of the most basic tasks related to creating such a video, is the spatial registration of the individual video stream prior to combining them into a new virtual video. At its core, this requires to estimate the pairwise relative geometry of images taken by different cameras. This is known as the relative pose problem [1], and is fundamental to many computer vision algorithms. In practice, efficiency and robustness is of highest relevance for big data applications as the ones address in the EU‐FET_SME project Scenenet. In this paper, we present an improved …